# Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks

Source: [Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks](<https://www.sota2.com/research/paper/68fa66201e209131cea0e849>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:43:30.383Z

Authors: Jianyu Wang, Haichao Zhang

Published: 2018-11-26T22:15:44.000Z

## Abstract

In this paper, we study fast training of adversarially robust models. From the analyses of the state-of-the-art defense method, i.e., the multi-step adversarial training, we hypothesize that the gradient magnitude links to the model robustness. Motivated by this, we propose to perturb both the image and the label during training, which we call Bilateral Adversarial Training (BAT). To generate the adversarial label, we derive an closed-form heuristic solution. To generate the adversarial image, we use one-step targeted attack with the target label being the most confusing class. In the experiment, we first show that random start and the most confusing target attack effectively prevent the label leaking and gradient masking problem. Then coupled with the adversarial label part, our model significantly improves the state-of-the-art results. For example, against PGD100 white-box attack with cross-entropy loss, on CIFAR10, we achieve 63.7\\% versus 47.2\\%; on SVHN, we achieve 59.1\\% versus 42.1\\%. At last, the experiment on the very (computationally) challenging ImageNet dataset further demonstrates the effectiveness of our fast method.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR-10 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test.md>): Image Classification; CIFAR-10 (test); Accuracy: 92.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1811.10716>)

[PDF](<https://arxiv.org/pdf/1811.10716.pdf>)
